Programming the Subsequent Technology of AI Purposes – O’Reilly

“Unusual was obliged to invent a lot of the magic he did, working from common rules and half-remembered tales from previous books.”

— Susanna Clarke, Jonathan Unusual & Mr Norrell

Fairy tales, myths, and fantasy fiction are stuffed with magic spells. You say “abracadabra” and one thing profound occurs.¹ Say “open sesame” and the door swings open.

It seems that that is additionally a helpful metaphor for what occurs with massive language fashions.

I first received this concept from David Griffiths’s O’Reilly course on using AI to boost your productivity. He gave a easy instance. You may inform ChatGPT “Set up my process listing utilizing the Eisenhower four-sided field.” And it simply is aware of what to do, even in the event you your self know nothing about Common Dwight D. Eisenhower’s method to determination making. David then suggests his college students as a substitute strive “Set up my process listing utilizing Getting Issues Performed,” or simply “Use GTD.” Every of these phrases is shorthand for programs of thought, practices, and conventions that the mannequin has discovered from human tradition.

These are magic phrases. They’re magic not as a result of they do one thing unworldly and sudden however as a result of they’ve the facility to summon patterns which were encoded within the mannequin. The phrases act as keys, unlocking context and even complete workflows.

All of us use magic phrases in our prompts. We are saying one thing like “Replace my resume” or “Draft a Substack publish” with out pondering how a lot detailed prompting we’d need to do to create that output if the LLM didn’t already know the magic phrase.

Each subject has a specialised language whose phrases are recognized solely to its initiates. We might be fanciful and fake they’re magic spells, however the actuality is that every of them can be a form of fuzzy perform name to an LLM, bringing in a physique of context and unlocking a set of behaviors and capabilities. Once we ask an LLM to jot down a program in Javascript fairly than Python, we’re utilizing one in every of these fuzzy perform calls. Once we ask for output as an .md file, we’re doing the identical. Not like a perform name in a standard programming language, it doesn’t all the time return the identical consequence, which is why builders have a chance to reinforce the magic.

From Prompts to Purposes

The following gentle bulb went off for me in a dialog with Claire Vo, the creator of an AI software referred to as ChatPRD. Claire spent years as a product supervisor, and as quickly as ChatGPT grew to become obtainable, started utilizing it to assist her write product requirement paperwork or PRDs. Each product supervisor is aware of what a PRD is. When Claire prompted ChatGPT to “write a PRD,” it didn’t want an extended preamble. That one acronym carried many years {of professional} observe. However Claire went additional. She refined her prompts, improved them, and taught ChatGPT suppose like her. Over time, she had educated a system, not on the mannequin degree, however on the degree of context and workflow.

Subsequent, Claire turned her workflow right into a product. That product is a software program interface that wraps up various associated magic phrases right into a helpful package deal. It controls entry to her custom-made magic spell, so to talk. Claire added detailed prompts, integrations with different instruments, entry management, and an entire lot of conventional programming in a next-generation software that makes use of a mixture of conventional software program code and “magical” fuzzy perform calls to an LLM. ChatPRD even interviews customers to be taught extra about their objectives, customizing the appliance for every group and use case.

Claire’s quickstart guide to ChatPRD is a good instance of what a magic-word (fuzzy perform name) software appears to be like like.

You may as well see how magic phrases are crafted into magic spells and the way these spells are even a part of the structure of functions like Claude Code by way of the explorations of builders like Jesse Vincent and Simon Willison.

In “How I’m Using Coding Agents in September, 2025,” Jesse first describes how his claude.md file supplies a base immediate that “encodes a bunch of course of documentation and guidelines that do a fairly good job preserving Claude on monitor.” After which his workflow calls on a bunch of specialised prompts he has created (i.e., “spells” that give clearer and extra customized that means to particular magic phrases) like “brainstorm,” “plan,” “architect,” “implement,” “debug,” and so forth. Notice how inside these prompts, he might use extra magic phrases like DRY, YAGNI, and TDD, which seek advice from particular programming methodologies. For instance, right here’s his planning immediate (boldface mine):

Nice. I want your assist to jot down out a complete implementation plan.

Assume that the engineer has zero context for our codebase and questionable
style. doc every part they should know. which recordsdata to the touch for every
process, code, testing, docs they could must test. check it.give
them the entire plan as bite-sized duties. DRY. YAGNI. TDD. frequent commits.

Assume they're a talented developer, however know nearly nothing about our
toolset or drawback area. assume they do not know good check design very
properly.

please write out this plan, in full element, into docs/plans/

However Jesse didn’t cease there. He constructed a undertaking referred to as Superpowers, which makes use of Claude’s recently announced plug-in architecture to “give Claude Code superpowers with a complete expertise library of confirmed methods, patterns, and instruments.” Announcing the project, he wrote:

Expertise are what give your brokers Superpowers. The primary time they actually popped up on my radar was a couple of weeks in the past when Anthropic rolled out improved Workplace doc creation. When the characteristic rolled out, I went poking round a bit – I requested Claude to inform me all about its new expertise. And it was only too happy to dish…. [Be sure to follow this link! – TOR]

One of many first expertise I taught Superpowers was How to create skills. That has meant that once I needed to do one thing like add git worktree workflows to Superpowers, it was a matter of describing how I needed the workflows to go…after which Claude put the items collectively and added a pair notes to the prevailing expertise that wanted to clue future-Claude into utilizing worktrees.

After studying Jesse’s publish, Simon Willison did a bit extra digging into the unique doc dealing with expertise that Claude had introduced and that had sparked Jesse’s brainstorm. He famous:

Expertise are extra than simply prompts although: the repository additionally consists of dozens of pre-written Python scripts for performing frequent operations.

 pdf/scripts/fill_fillable_fields.py for instance is a customized CLI device that makes use of pypdf to seek out after which fill in a bunch of PDF type fields, specified as JSON, then render out the ensuing mixed PDF.

It is a actually refined set of instruments for doc manipulation, and I really like that Anthropic have made these seen—presumably intentionally—to customers of Claude who know ask for them.

You may see what’s occurring right here. Magic phrases are being enhanced and given a extra rigorous definition, and new ones are being added to what, in fantasy tales, they name a “grimoire,” or e book of spells. Microsoft calls such spells “metacognitive recipes,” a beautiful time period that ought to get extensively adopted, although on this article I’m going to stay with my fanciful analogy to magic.

At O’Reilly, we’re working with a really completely different set of magic phrases. For instance, we’re constructing a system for exactly focused competency-based studying, by way of which our prospects can skip what they already know, grasp what they want, and show what they’ve discovered. It additionally offers company studying system managers the flexibility to assign studying objectives and to measure the ROI on their funding.

It seems that there are dozens of studying frameworks (and that’s itself a magic phrase). Within the design of our personal specialised studying framework, we’re invoking Bloom’s taxonomy, SFIA, and the Dreyfus Mannequin of Ability Acquisition. However when a buyer says, “We love your method, however we use LTEM,” we are able to invoke that framework as a substitute. Each company buyer additionally has its personal specialised tech stack. So we’re exploring use magic phrases to let no matter we construct adapt dynamically not solely to our finish customers’ studying wants however to the tech stack and to the training framework that already exists at every firm.

That will be a nightmare if we needed to assist dozens of various studying frameworks utilizing conventional processes. However the issue appears rather more tractable if we’re in a position to invoke the precise magic phrases. That’s what I imply once I say that magic phrases are a vital constructing block within the subsequent technology of software programming.

The Structure of Magic

Right here’s the necessary factor: Magic isn’t arbitrary. In each mythic custom, it has construction, self-discipline, and value. The magician’s energy will depend on understanding the precise phrases, pronounced in the precise method, with the precise intent.

The identical is true for AI programs. The effectiveness of our magic phrases will depend on context, grounding, and suggestions loops that give the mannequin dependable details about the world.

That’s why I discover the rising ecosystem of AI functions so fascinating. It’s about offering the precise context to the mannequin. It’s about defining vocabularies, workflows, and roles that expose and make sense of the mannequin’s talents. It’s about turning implicit cultural information into express programs of interplay.

We’re solely at first. However simply as early programmers discovered to construct structured software program with out spelling out precise machine directions, as we speak’s AI practitioners are studying to construct structured reasoning programs out of fuzzy language patterns.

Magic phrases aren’t only a poetic picture. They’re the syntax of a brand new form of computing. As individuals grow to be extra comfy with LLMs, they may go across the magic phrases they’ve discovered as energy consumer tips. In the meantime, builders will wrap extra superior capabilities round present magic phrases and maybe even educate the fashions new ones that haven’t but had the time to accrete adequate that means by way of vast utilization within the coaching set. Every software shall be constructed round a shared vocabulary that encodes its area information. Again in 2022, Mike Loukides referred to as these programs “formal informal languages.” That’s, they’re spoken in human language, however do higher once you apply a little bit of rigor.

And at the least for the foreseeable future, builders will write “shims” between the magic phrases that management the LLMs and the extra conventional programming instruments and methods that interface with present programs, a lot as Claire did with ChatPRD. However finally we’ll see true AI to AI communication.

Magic phrases and the spells constructed round them are solely the start. As soon as individuals begin utilizing them in frequent, they grow to be protocols. They outline how people and AI programs cooperate, and the way AI programs cooperate with one another.

We are able to already see this occurring. Frameworks like LangChain or the Mannequin Context Protocol (MCP) formalize how context and instruments are shared. Groups construct agentic workflows that rely upon a typical vocabulary of intent. What’s an MCP server, in any case, however a mapping of a fuzzy perform name right into a set of predictable instruments and companies obtainable at a given endpoint?

In different phrases, what was as soon as a set of magic spells is changing into infrastructure. When sufficient individuals use the identical magic phrases, they cease being magic and begin being requirements—the constructing blocks for the following technology of software program.

We are able to already see this development with MCP. There are three distinct sorts of MCP servers. Some, like Playwright MCP, are designed to make it simpler for AIs to interface with functions initially designed for interactive human use. Others, just like the GitHub MCP Server, are designed to make it simpler for AIs to interface with present APIs, that’s, with interfaces initially designed to be referred to as by conventional packages. However some are designed as a frontend for a real AI-to-AI dialog. Different protocols, like A2A, are already optimized for this third use case.

However in every case, an MCP server can be a dictionary (or in magic phrases, a spellbook)  that explains the magic phrases that it understands and invoke them. As Jesse Vincent put it to me after studying a draft of this piece:

The half that feels probably the most like magic spells is the half that almost all MCP authors do extremely poorly. Every device has a “description” subject that tells the LLM how you utilize the device. That description subject is learn and internalized by the LLM and modifications the way it behaves. Anthropic are notably good at device descriptions and most everyone else, in my expertise, is…much less good.

In some ways, publishing the prompts, device descriptions, context, and expertise that add performance to LLMs could also be a extra necessary frontier of open supply AI than open weights. It’s necessary that we deal with our enhancements to magic phrases not as proprietary secrets and techniques however as shared cultural artifacts. The extra open and participatory our vocabularies are, the extra inclusive and artistic the ensuing ecosystem shall be.

Footnotes

1. Whereas typically related as we speak with stage magic and cartoons, this magic phrase was apparently used from Roman occasions as a therapeutic spell. One proposed etymology means that it comes from the Aramaic for “I create as I speak.”